dimensionality reduction
Dimensionality reduction is a technique used to reduce the number of features (dimensions) in a dataset while preserving important information. This is particularly useful in high-dimensional spaces to improve model performance and visualization clarity.
- Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-Index Models
- AutoSciDACT: Automated Scientific Discovery through Contrastive Embedding and Hypothesis Testing
- DCA: Graph-Guided Deep Embedding Clustering for Brain Atlases
- GAMMA: Gated Multi-hop Message Passing for Homophily-Agnostic Node Representation in GNNs
- IMPACT: Irregular Multi-Patch Adversarial Composition Based on Two‑Phase Optimization
- Johnson-Lindenstrauss Lemma Beyond Euclidean Geometry
- Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations
- Reverse-Annealed Sequential Monte Carlo for Efficient Bayesian Optimal Experiment Design
- SD-KDE: Score-Debiased Kernel Density Estimation
- Stabilizing LTI Systems under Partial Observability: Sample Complexity and Fundamental Limits
- The Cost of Compression: Tight Quadratic Black-Box Attacks on Sketches for $\ell_2$ Norm Estimation
- The Generative Leap: Tight Sample Complexity for Efficiently Learning Gaussian Multi-Index Models
- Understanding Contrastive Learning via Gaussian Mixture Models